test

图像处理的简单程序，适合初学者，自己好好看看(Simple image processing procedures, suitable for beginners, its a good look)

说明：  利用全卷积神经网络，实现图像的语义分割，基于tensorflow的keras可以直接运行(Using the full convolutional neural network to achieve semantic segmentation of images, keras based on tensorflow can be run directly)

绣花问题是连续型的填充，在不同区域的缝制过程中，缝针不能提针，因此不能用一般的离散型区 域填充方法处理。本文运用几何计算和图论理论提出了一个绣花缝针轨迹自动生成算法：先对轮廓走向进行 定义，通过轮廓铅垂方向的局部极值点的分割线将图案从上向下进行分割，采用交点的特征值比较彻底的解 决了分割时的重点问题，将图案区域准确的划分成缝针能一次完成的若干个节点。在此基础上根据节点的邻 接关系建立节点的邻接“图”，通过图论中半哈密尔顿路径或深度遍历方法找到节点的遍历（缝制）序列和每 个节点的缝制方向，最后可对设定的起点、终点和缝针间隔的条件自动提供缝针的走向轨迹。(In the process of embroidering, needle can not hang up for changing to a different area. Therefore, Embroider problem could be abstract as a continuous area-filling work. Considering disperse area-filling methods can not process this problem well. Based on geometry computing and graph theory, an algorithm of finding path of embroidering needle are proposed in this paper. First, outline orientations are defined, and finding all local extreme points of inner outline on their gravitational orientation to build sectioning lines so as to divide the picture. By using intersection point character the overlap point problem was solved perfectly. Therefore, the picture is divided into some nodes which can be finished alone. Then, based on connections of these nodes, an adjacency graph of nodes was built. Using half-Hamilton path or depth-first search method, both embroidering sequence and direction of these nodes could be got from the graph. Finally, from a defined start-point, end-point)

关于基于Kruppa方程的摄像机自标定方法的两篇论文，相对于传统的标校方法，是一种新的相机自标定技术(About Kruppa equation based camera self-calibration method of two papers, as opposed to the traditional Calibration Method is a new camera self-calibration technique)

根据论文Curvature Scale Space Corner Detector with Adaptive Threshold and Dynamic Region of Support算法写的角点检测(err)

matlab提取图像的纹理特征，包括方差、熵、角二阶矩等特征。(matlab extract the texture features, including variance, entropy, angular second moment and other features.)

说明：  光流计算得到运动场。使用算法为Lucas Kanade算法。(optical flow calculated Sports Ground. Lucas uses algorithms to Kanade algorithm.)

图像去模糊处理，分别运用了维纳滤波器、deconvreg方法、deconvlucy方法、盲反卷积等方法。非常实用(Image deblurring processing, namely the use of the Wiener filter, deconvreg method, deconvlucy methods, blind deconvolution methods. Very useful)

图像处理的峰值信噪比计算程序，简单精确，直接算出值(PSNR calculation program image processing, simple accurate, direct calculation value)

读取MODIS的HDF文件和ENVI IDL的程序(MODIS ENVI IDL readhdf.pro)